INDEX

Explanations

interactions and relationships between characters in a narrative, particularly focusing on emotional exchanges and personal dynamics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

emez

-0.17

-0.15

shal

-0.14

lanÄ±r

-0.14

·»

-0.14

ãĥªãĤ¹

-0.14

ê·¹

-0.14

åħ¸

-0.14

.Arg

-0.13

ilian

-0.13

POSITIVE LOGITS

 meant

0.23

 intended

0.19

 intend

0.18

 intends

0.17

ubbo

0.17

 intentions

0.16

 intent

0.16

 means

0.16

 intention

0.16

Care

0.16

Activations Density 0.217%

interactions and relationships between characters in a narrative, particularly focusing on emotional exchanges and personal dynamics

No Comments

No Known Activations